A
A
Antonio06082022-04-10 14:58:31
Python
Antonio0608, 2022-04-10 14:58:31

Bugs in Theano and Tensorflow?

Studying machine learning (self-taught) I accidentally encountered such a problem.
Why does the same NS on different backends work, then it gives an error.
For example.
I took the usual NS from the Internet (some lessons).
And found that
Theano backend:
Everything works well.
And Tensorflow backend:
Throws an error.
TypeError: 'int' object is not iterable.

from numpy import array
from numpy import hstack
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.preprocessing.sequence import TimeseriesGenerator
# define dataset
in_seq1 = array([10, 20, 30, 40, 50, 60, 70, 80, 90, 100])
in_seq2 = array([15, 25, 35, 45, 55, 65, 75, 85, 95, 105])
# reshape series
in_seq1 = in_seq1.reshape((len(in_seq1), 1))
in_seq2 = in_seq2.reshape((len(in_seq2), 1))
# horizontally stack columns
dataset = hstack((in_seq1, in_seq2))
# define generator
n_features = dataset.shape[1]
n_input = 2
generator = TimeseriesGenerator(dataset, dataset, length=n_input, batch_size=8)
# define model
model = Sequential()
model.add(LSTM(100, activation='relu', input_shape=(n_input, n_features)))
model.add(Dense(2))
model.compile(optimizer='adam', loss='mse')
# fit model
model.fit_generator(generator, steps_per_epoch=1, epochs=500, verbose=0)
# make a one step prediction out of sample
x_input = array().reshape((1, n_input, n_features))
yhat = model.predict(x_input, verbose=0)
print(yhat)

Why is not clear.
I searched the Internet for an answer.
It seems that the error is related to the for(range) loop. but there is no such thing.
What to do?

Answer the question

In order to leave comments, you need to log in

Didn't find what you were looking for?

Ask your question

Ask a Question

731 491 924 answers to any question